The track Mood by 24kGoldn ft. iann diorr is also one of the identified popular tracks in the corpus. A keygram and chordogram are plotted in order to show the tonal progression of the track by estimating the chords and key for each segment.
Spotify API
According to the Spotify API, this track is in the 7th key, with mode 0: meaning G minor.
Chordify
The Chordify algorithm identified the chords the following (4/4) loop:
The identified key appears to be on the natural scale:
G - A - B♭ - C - D - E♭ - F
The COVID-19 pandemic has stirred society up by quite large margin. Many people are directly or indirectly affected by the health crisis or the resulting governmental measures in some form or another. This has caused society to adjust, namely in social distancing and isolation. Demanding society to change we communicate, work and more aspects of daily life. This dashboard will focus on the effects of the pandemic on the music listening behavior of Spotify users in the Netherlands, and will explore the main question below.
Did Spotify users in the Netherlands change their music listening behavior during the COVID-19 pandemic?
A corpus consisting of different portfolio’s has been be created to perform various analyses using the Spotify API. This portfolio will mainly on focus on the music listening behavior of Spotify users in the Netherlands before and during the COVID-19 pandemic, as measured by the Spotify API. In addition, specific events on specific times will be highlighted in order to find out to what extent changes in listening behavior can be attributed to certain government imposed measures (e.g. lockdown and curfew).
Corpus
In order to analyze general listening behavior, the most important variables for the analyses are:
Playlist
In order to keep track on the average listening behavior of Dutch Spotify users, the weekly ‘Top 50’ and ‘Viral 50’ playlists from the Netherlands will be analyzed over time. The year 2019 will be measured from week 45, the year 2020 in its entirety, and 2021 is measured until week 7.
Thus,
2019 contains 8 playlists consisting of 50 observations (tracks)
2020 contains 53 playlists consisting of 50 observations (tracks)
2021 contains 7 playlists consisting of 50 observations (tracks)
Since Spotify autoupdates their playlists, the historical ‘Top 50’ lists in the form of CSV files will be retrieved from Spotify Charts.
Spotify Audio Features
The changes of (or lack thereof) listening behavior will be measured by the the different Audio Features provided by the Spotify API The Spotify Audio Features consists of the following features:
Also the following features obtained through the Spotify API will be analyzed:
The mean of each variable of the 50 tracks will be calculated, outliers and other interesting tracks in the dataset will be highlighted as well.
Time
The variable time will be used to identify the different weeks as well as the periods before and during the pandemic that may explain the changes in music listening behavior from the top and viral playlists. In addition interesting annual periods will be isolated to see if similar patterns reoccur during the pandemic.For example, the December Holiday season before and during the pandemic will be analyzed to identify whether Spotify users altered their Christmas related listening behavior.
COVID-19 variables
Alongside the musical analyses the statistics concerning COVID-19 will be taken into account. The data is provided by the The Dutch National Institute for Public Health and the Environment (RIVM). The data has been pre-processed to include weekly and cumulative data. The variables that are included in this dashboard are the following variables:
On February 27th, 2020 (week 9), the first case of COVID-19 had been confirmed in the Netherlands. Before this occurrence, when everything was normal, the number of streams of the top songs decreased until the end of the holiday season. Probably due people coming together to enjoy (the holiday) music, movies or other activities together, instead of individually. In the first few weeks of 2021 the number of streams started rising again.
From week 5 the number of top streams started to decline. And even When the first cases, the first admissions into the hospitals, and first deaths were reported the number continued to decline.
As the situation became more severe, with record COVID-related hostpital admissions in week 13, the Dutch government implemented the ‘intelligent’ lockdown (dotted vertical line). This led to a relative high public solidarity towards those affected by the virus, especially essential workers. This may explain the sudden spike of the top stream from 1,598,458 to a record 3,482,822 streams within two weeks, with the song 17 Miljoen Mensen - Live @538 in Ahoy by Davina Michelle topping the charts for five consecutive weeks. 17 Miljoen Mensen (17 Million people) was dedicated to the people affected by the virus. So this spike is most likely related to the virus and its effects.
In the corpus there are a total of 20 distinct tracks topping that charts in a span of 68 weeks. On average a Top 1 track remains for 3.4 weeks on the number 1 spot, while streamed 6502808 times, and 1773952 times per week on the Top 1 spot.
This gives an interesting insight to the weekly most popular songs in this corpus. But which track is the most popular? Since the corpus is time constrained, solely considering the number of streams might not show the full picture. Therefore, three variables are considered:
The most popular song according to variable 1 is “Dance Monkey” by Tones And I, with a total of 15,872,577 streams while at number 1. The other variables (v2 = 8 weeks | v3 = 1,984,072 per week) show that the track performs above average and can indeed be considered popular.
According to variable 2, “Mood (feat. iann dior)” by 24kGoldn is the most popular, topping the charts for a total of 9 weeks. The other variables (v1 = 15,498,940 | v3 = 1,722,104 per week) show that it is significantly popular under v1, but barely underperforms under v3.
Variable 3 shows “Tigers” by Bilal Wahib is streamed the most per week while on top with 2,652,339 streams. The track underperforms on the other variables (v1 = 5,304,679 | v2 = 2 weeks). Thus, this song can be considered a viral hit or more harshly a “one hit wonder” lasting two weeks.
There are limitations to this approach, only the number one spots are considere. For a clearer picture,a wider range is recommended. The tracks “Dance Monkey” and “Mood” performed quite similarly. It remains difficult to denote which song is the most popular.
The track “17 Miljoen Mensen” (2021) is actually a cover of “15 Miljoen Mensen” (1996), which was released 25 years earlier! An analysis of the chromafeatures of the two tracks made in order to find similarities between them. Instantly noticed differences are 17 Miljoen mensen’s title adjustment for the population increase of 2 million people, and its shortness with a duration of just 1 minute and 47 seconds.
The first plot shows the Dynamic Time Warping of the two tracks, using Euclidean norm and angular distance. A diagonal pattern would denote similarity between the two tracks. This is not observed, which implies significant differences. For instance, the table below shows that pitch classes differ. According to the Spotify API, “17 Miljoen Mensen” is in the key of G major, wheras “15 Miljoen Mensen” is in the key of C major. This is not explicitly shown in the two chromagrams, but the keys do display brief high magnitude of the course of their songs respectively.
The tracks do share a In addition the ‘sound and feel’ of the tracks differ: 15 miljoen mensen has a higher danceability, energy, and loudness, whereas “17 miljoen mensen” has a much higher acousticness and liveness (due to the recording being a live performance). A remarkable commonality probably explains the differences: Both tracks were unintended single releases, “15 miljoen mensen” was initially written for a commercial, and “17 Miljoen mensen” as a tribute for a (due to COVID-19) canceled music concert. The different motivations behind the tracks reflects the different ‘sound and feel’ as shown by Spotify API.
| 17 Miljoen Mensen (2021) | 15 Miljoen Mensen (1996) | |
|---|---|---|
| danceability | 0.493 | 0.547 |
| energy | 0.321 | 0.631 |
| key | 7 | 0 |
| loudness | -10.041 | -7.063 |
| mode | 1 | 1 |
| speechiness | 0.0402 | 0.0266 |
| acousticness | 0.715 | 0.0943 |
| instrumentalness | 0 | 0 |
| liveness | 0.0863 | 0.0548 |
| valence | 0.508 | 0.481 |
| tempo | 86.77 | 79.02 |
| duration_sec | 107.2 | 236.107 |
| time_signature | 4 | 4 |
Christmas songs started to dominate the charts in 2020 around week 49 until week 53, whereas in 2019 Christmas this phenomenon occurred much later. In 2020 it is noticeable that the bottom corner with tracks with relatively high BPM, high valence, low energy and low danceability are from the weeks when Christmas tracks dominated the charts. In 2019 this phenomenon is very noticeable in week 52, but shows that Christmas started in week 50, but less prevalent than in 2020. Also in 2020, the charts remained similar during the holiday period, whereas in 2019, it suddenly shot up (or downwards as shown in the plot) in week 52.
Interestingly, Mariah Carey’s ‘All I Want for Christmas’ topped the charts for four consecutive weeks in 2020, as opposed to 1 week in 2019.
A Possible explanation is that due to the imposed lockdown and other restrictions, people may have felt a need or desire for the “Christmas Spirit” or “Christmas Vibes” a week earlier than in 2019.
Another interesting discovery is that similar in 2019 the top streams in 2020 decreased in similar fashion. A possible explanation is that people disregarded the lockdown regulations and spent the holiday season with friend and/or family. Another is that people we’re occupied with other activities to keep in touch with their friends and family.
“Dance Monkey” by Tones And I is one of the most popular tracks within the corpus. A structure analysis will show possible patterns of sequences within the track and their relation.
The first cepstrogram plot shows the magnitude of each timbre feature per segment of the track. The feature c01 is loudness, c02 is low frequency, c03 is mid frequencies. c04 and up are not defined as straight forward, but they may be implied by keeping track of changes within a track during specific segments. The cepstrogram shows that "Dance Monkey’s timbre features are relatively more defined by c01 to c05.
The second and third plots are Self Similarity Matrices (SSM); The first being pitch, and the second timbre. These plots show the structure of a track by denoting patterns of similarities that reoccur. Diagonal lines and a checkerboard pattern show similarity and repetition.
The timbre SSM is plotted using Euclidean norm, Euclidean distance and summarized by the mean. The plot shows a faint checkerboard pattern which implies some form of repetition in the track. At the 150 second mark there is a significant timbre difference. This is when the breakdown occurs with the earlier mentioned “Millenial Whoop”.
The pitch SSM is plotted using Euclidean norm, cosine distance and summarized by root mean square. This plot shows a slightly more noticeable checkerboard pattern. At the 150 second mark, the plot shows a significant change.